System-Level Simulation of Hardware Spiking Neural Network Based on Synaptic Transistors and I&amp;F Neuron Circuits

Hwang, Sungmin; Kim, Hyungjin; Park, Jungjin; Kwon, Min-Woo; Baek, Myung-Hyun; Lee, Jeong-Jun

doi:10.1109/led.2018.2853635

Cited by 40 publications

(22 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main components of the brain are neurons, which process information, and synapses, which learn and remember by adjusting their connection strength. In particular, neurons are often regarded as stochastic spiking elements that transmit digital signals across analog synapses, whose conductance can take on a range of values (Hwang et al, 2018;Kwon et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Anisotropy and Current Control of Magnetization in SrRuO3/SrTiO3 Heterostructures for Spin-Memristors

Goossens

Leiviskä

Banerjee

2021

Front. Nanotechnol.

View full text Add to dashboard Cite

Spintronics-based nonvolatile components in neuromorphic circuits offer the possibility of realizing novel functionalities at low power. Current-controlled electrical switching of magnetization is actively researched in this context. Complex oxide heterostructures with perpendicular magnetic anisotropy (PMA), consisting of SrRuO3 (SRO) grown on SrTiO3 (STO) are strong material contenders. Utilizing the crystal orientation, magnetic anisotropy in such simple heterostructures can be tuned to either exhibit a perfect or slightly tilted PMA. Here, we investigate current induced magnetization modulation in such tailored ferromagnetic layers with a material with strong spin-orbit coupling (Pt), exploiting the spin Hall effect. We find significant differences in the magnetic anisotropy between the SRO/STO heterostructures, as manifested in the first and second harmonic magnetoresistance measurements. Current-induced magnetization switching can be realized with spin-orbit torques, but for systems with perfect PMA this switching is probabilistic as a result of the high symmetry. Slight tilting of the PMA can break this symmetry and allow the realization of deterministic switching. Control over the magnetic anisotropy of our heterostructures therefore provides control over the manner of switching. Based on our findings, we propose a three-terminal spintronic memristor, with a magnetic tunnel junction design, that shows several resistive states controlled by electric charge. Non-volatile states can be written through SOT by applying an in-plane current, and read out as a tunnel current by applying a small out-of-plane current. Depending on the anisotropy of the SRO layer, the writing mechanism is either deterministic or probabilistic allowing for different functionalities to emerge. We envisage that the probabilistic MTJs could be used as synapses while the deterministic devices can emulate neurons.

show abstract

Section: Introductionmentioning

confidence: 99%

Anisotropy and Current Control of Magnetization in SrRuO3/SrTiO3 Heterostructures for Spin-Memristors

Goossens

Leiviskä

Banerjee

2021

Front. Nanotechnol.

View full text Add to dashboard Cite

show abstract

“…As one of the candidate methods for training SNNs, it was studied to transfer the weights trained by the ANN to the SNN [3], [4]. The conventional ReLU activation function can be approximated by a combination of the integrate and fire (I&F) neurons and the rate-encoding method that expresses the analog-valued input as the frequency of the input pulse in the SNN [5]. Due to this approximation, the SNN can achieve the performance of a highly advanced ANN without significant degradation and can greatly improve the learning speed by using GPU-accelerated training packages.…”

Section: Introductionmentioning

confidence: 99%

Spiking Neural Networks With Time-to-First-Spike Coding Using TFT-Type Synaptic Device Model

Soo-Chang

Woo

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

In hardware-based spiking neural networks (SNNs), the conversion of analog input data into the arrival time of an input pulse is regarded as a good candidate for the encoding method due to its bioplausibility and power-efficiency. In this work, we trained an SNN encoded by time to first spike (TTFS) and performed an inference process using the behavior of the fabricated TFT-type flash synaptic device. The exponentially decaying synaptic current model required in the inference process was implemented by reading devices in the subthreshold region using triangle pulses. In a high-level system simulation, the TTFS-SNN (two-layer MLP with 512 hidden neurons) reached a high accuracy of 97.94%. Compared to conventional rate-encoded SNNs, TTFS-SNN made 2.9 times faster judgment and consumed ~10 times less energy in the inference process. Additionally, to use the network in a more stable condition, we propose a method to operate it using a rectangle pulse in the saturation region of the synaptic device. The distortion caused by this approximation was minimized by shortening the pulse width. As a result, the modified inference system showed an accuracy of 97.36%, and the prediction time and energy consumption were reduced 3.97-and 83.04-times when compared to those of the rate-SNN. Finally, we analyzed the sensitivity of the network performance due to unexpected issues that may occur in the hardware system and thus explained the competitiveness of the proposed synaptic behavior in the saturation region.

show abstract

“…However, an inevitable bottleneck of the von Neumann architecture due to the data transfer between processing and memory elements has become a major factor causing significant latency and power consumption [2]. Neuromorphic system is a potential candidate for beyond von Neumann computing era to solve this issue by mimicking a massively parallel processing of biological nervous systems and has recently gained interest by demonstrating cognitive functions including pattern recognition [3][4][5][6][7][8][9][10][11][12][13]. Since synaptic devices play a key role of not only storing information but also constructing neural network and transferring signals, various kinds of artificial synaptic devices have been investigated and demonstrated including memristors and transistors [14][15][16][17][18][19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Digital and Analog Switching Characteristics of InGaZnO Memristor Depending on Top Electrode Material for Neuromorphic System

et al. 2020

Self Cite

View full text Add to dashboard Cite

In this study, we demonstrate both of digital and analog memory operations in InGaZnO (IGZO) memristor devices by controlling the electrode materials for neuromorphic application. The switching properties of the devices are determined by the initial energy barrier characteristics between the metal electrodes and the IGZO switching layer. Digital switching characteristics are obtained after the forming process when Schottky junction occurs at both of top and bottom electrodes. On the other hands, analog resistive switching is achieved when Schottky and Ohmic junctions exist at each side because the applied voltage modulates the Schottky barrier height through the Ohmic contact. In addition, the weightupdate properties of the devices are verified depending on identical and incremental pulse schemes. The incremental pulse trains improve the linearity and variation of weight modulation, leading to the stable learning characteristics of neuromorphic system in terms of pattern recognition with MNIST handwritten digit images.

show abstract

System-Level Simulation of Hardware Spiking Neural Network Based on Synaptic Transistors and I&F Neuron Circuits

Cited by 40 publications

References 28 publications

Anisotropy and Current Control of Magnetization in SrRuO3/SrTiO3 Heterostructures for Spin-Memristors

Anisotropy and Current Control of Magnetization in SrRuO3/SrTiO3 Heterostructures for Spin-Memristors

Spiking Neural Networks With Time-to-First-Spike Coding Using TFT-Type Synaptic Device Model

Digital and Analog Switching Characteristics of InGaZnO Memristor Depending on Top Electrode Material for Neuromorphic System

Contact Info

Product

Resources

About